diff --git a/RunGrepTest b/RunGrepTest index 78206ba..25f69bd 100755 --- a/RunGrepTest +++ b/RunGrepTest @@ -558,7 +558,7 @@ echo "RC=$?" >>testtrygrep echo "---------------------------- Test 107 -----------------------------" >>testtrygrep echo "a" >testtemp1grep echo "aaaaa" >>testtemp1grep -(cd $srcdir; $valgrind $vjs $pcre2grep --line-offsets '(?<=\Ka)' $builddir/testtemp1grep) >>testtrygrep 2>&1 +(cd $srcdir; $valgrind $vjs $pcre2grep --line-offsets --allow-lookaround-bsk '(?<=\Ka)' $builddir/testtemp1grep) >>testtrygrep 2>&1 echo "RC=$?" >>testtrygrep echo "---------------------------- Test 108 ------------------------------" >>testtrygrep @@ -638,13 +638,13 @@ echo "RC=$?" >>testtrygrep echo "---------------------------- Test 125 -----------------------------" >>testtrygrep printf 'abcd\n' >testNinputgrep -$valgrind $vjs $pcre2grep --colour=always '(?<=\K.)' testNinputgrep >>testtrygrep +$valgrind $vjs $pcre2grep --colour=always --allow-lookaround-bsk '(?<=\K.)' testNinputgrep >>testtrygrep echo "RC=$?" >>testtrygrep -$valgrind $vjs $pcre2grep --colour=always '(?=.\K)' testNinputgrep >>testtrygrep +$valgrind $vjs $pcre2grep --colour=always --allow-lookaround-bsk '(?=.\K)' testNinputgrep >>testtrygrep echo "RC=$?" >>testtrygrep -$valgrind $vjs $pcre2grep --colour=always '(?<=\K[ac])' testNinputgrep >>testtrygrep +$valgrind $vjs $pcre2grep --colour=always --allow-lookaround-bsk '(?<=\K[ac])' testNinputgrep >>testtrygrep echo "RC=$?" >>testtrygrep -$valgrind $vjs $pcre2grep --colour=always '(?=[ac]\K)' testNinputgrep >>testtrygrep +$valgrind $vjs $pcre2grep --colour=always --allow-lookaround-bsk '(?=[ac]\K)' testNinputgrep >>testtrygrep echo "RC=$?" >>testtrygrep echo "---------------------------- Test 126 -----------------------------" >>testtrygrep @@ -701,7 +701,7 @@ if [ $utf8 -ne 0 ] ; then echo "RC=$?" >>testtrygrep echo "---------------------------- Test U3 ------------------------------" >>testtrygrep - (cd $srcdir; $valgrind $vjs $pcre2grep --line-offsets -u --newline=any '(?<=\K\x{17f})' ./testdata/grepinput8) >>testtrygrep + (cd $srcdir; $valgrind $vjs $pcre2grep --line-offsets -u --newline=any --allow-lookaround-bsk '(?<=\K\x{17f})' ./testdata/grepinput8) >>testtrygrep echo "RC=$?" >>testtrygrep echo "---------------------------- Test U4 ------------------------------" >>testtrygrep diff --git a/doc/html/pcre2grep.html b/doc/html/pcre2grep.html index 995e0ea..b3252d3 100644 --- a/doc/html/pcre2grep.html +++ b/doc/html/pcre2grep.html @@ -188,6 +188,12 @@ Treat binary files as text. This is equivalent to --binary-files=text.

+--allow-lookaround-bsk +PCRE2 now forbids the use of \K in lookarounds by default, in line with Perl. +This option causes pcre2grep to set the PCRE2_EXTRA_ALLOW_LOOKAROUND_BSK +option, which enables this somewhat dangerous usage. +

+

-B number, --before-context=number Output up to number lines of context before each matching line. Fewer lines are output if the previous match or the start of the file is within @@ -1040,16 +1046,16 @@ because VMS does not distinguish between exit(0) and exit(1).

Philip Hazel
-University Computing Service +Retired from University Computing Service
Cambridge, England.


REVISION

-Last updated: 04 October 2020 +Last updated: 31 August 2021
-Copyright © 1997-2020 University of Cambridge. +Copyright © 1997-2021 University of Cambridge.

Return to the PCRE2 index page. diff --git a/doc/pcre2grep.1 b/doc/pcre2grep.1 index 66377ce..1081591 100644 --- a/doc/pcre2grep.1 +++ b/doc/pcre2grep.1 @@ -1,4 +1,4 @@ -.TH PCRE2GREP 1 "04 October 2020" "PCRE2 10.36" +.TH PCRE2GREP 1 "31 August 2021" "PCRE2 10.38" .SH NAME pcre2grep - a grep with Perl-compatible regular expressions. .SH SYNOPSIS @@ -157,6 +157,11 @@ is expected to be relatively small. When \fB-c\fP is used, \fB-A\fP is ignored. Treat binary files as text. This is equivalent to \fB--binary-files\fP=\fItext\fP. .TP +\fB--allow-lookaround-bsk\fP +PCRE2 now forbids the use of \eK in lookarounds by default, in line with Perl. +This option causes \fBpcre2grep\fP to set the PCRE2_EXTRA_ALLOW_LOOKAROUND_BSK +option, which enables this somewhat dangerous usage. +.TP \fB-B\fP \fInumber\fP, \fB--before-context=\fP\fInumber\fP Output up to \fInumber\fP lines of context before each matching line. Fewer lines are output if the previous match or the start of the file is within @@ -946,7 +951,7 @@ because VMS does not distinguish between exit(0) and exit(1). .sp .nf Philip Hazel -University Computing Service +Retired from University Computing Service Cambridge, England. .fi . @@ -955,6 +960,6 @@ Cambridge, England. .rs .sp .nf -Last updated: 04 October 2020 -Copyright (c) 1997-2020 University of Cambridge. +Last updated: 31 August 2021 +Copyright (c) 1997-2021 University of Cambridge. .fi diff --git a/doc/pcre2grep.txt b/doc/pcre2grep.txt index 0e839c7..8e9c757 100644 --- a/doc/pcre2grep.txt +++ b/doc/pcre2grep.txt @@ -158,110 +158,116 @@ OPTIONS Treat binary files as text. This is equivalent to --binary- files=text. + --allow-lookaround-bsk + PCRE2 now forbids the use of \K in lookarounds by default, in + line with Perl. This option causes pcre2grep to set the + PCRE2_EXTRA_ALLOW_LOOKAROUND_BSK option, which enables this + somewhat dangerous usage. + -B number, --before-context=number - Output up to number lines of context before each matching - line. Fewer lines are output if the previous match or the - start of the file is within number lines, or if the process- - ing buffer size has been set too small. If file names and/or + Output up to number lines of context before each matching + line. Fewer lines are output if the previous match or the + start of the file is within number lines, or if the process- + ing buffer size has been set too small. If file names and/or line numbers are being output, a hyphen separator is used in- - stead of a colon for the context lines. A line containing - "--" is output between each group of lines, unless they are - in fact contiguous in the input file. The value of number is - expected to be relatively small. When -c is used, -B is ig- + stead of a colon for the context lines. A line containing + "--" is output between each group of lines, unless they are + in fact contiguous in the input file. The value of number is + expected to be relatively small. When -c is used, -B is ig- nored. --binary-files=word - Specify how binary files are to be processed. If the word is - "binary" (the default), pattern matching is performed on bi- - nary files, but the only output is "Binary file - matches" when a match succeeds. If the word is "text", which - is equivalent to the -a or --text option, binary files are - processed in the same way as any other file. In this case, - when a match succeeds, the output may be binary garbage, - which can have nasty effects if sent to a terminal. If the - word is "without-match", which is equivalent to the -I op- + Specify how binary files are to be processed. If the word is + "binary" (the default), pattern matching is performed on bi- + nary files, but the only output is "Binary file + matches" when a match succeeds. If the word is "text", which + is equivalent to the -a or --text option, binary files are + processed in the same way as any other file. In this case, + when a match succeeds, the output may be binary garbage, + which can have nasty effects if sent to a terminal. If the + word is "without-match", which is equivalent to the -I op- tion, binary files are not processed at all; they are assumed - not to be of interest and are skipped without causing any + not to be of interest and are skipped without causing any output or affecting the return code. --buffer-size=number - Set the parameter that controls how much memory is obtained + Set the parameter that controls how much memory is obtained at the start of processing for buffering files that are being scanned. See also --max-buffer-size below. -C number, --context=number - Output number lines of context both before and after each - matching line. This is equivalent to setting both -A and -B + Output number lines of context both before and after each + matching line. This is equivalent to setting both -A and -B to the same value. -c, --count - Do not output lines from the files that are being scanned; - instead output the number of lines that would have been + Do not output lines from the files that are being scanned; + instead output the number of lines that would have been shown, either because they matched, or, if -v is set, because - they failed to match. By default, this count is exactly the - same as the number of lines that would have been output, but - if the -M (multiline) option is used (without -v), there may - be more suppressed lines than the count (that is, the number + they failed to match. By default, this count is exactly the + same as the number of lines that would have been output, but + if the -M (multiline) option is used (without -v), there may + be more suppressed lines than the count (that is, the number of matches). - If no lines are selected, the number zero is output. If sev- - eral files are are being scanned, a count is output for each - of them and the -t option can be used to cause a total to be - output at the end. However, if the --files-with-matches op- - tion is also used, only those files whose counts are greater + If no lines are selected, the number zero is output. If sev- + eral files are are being scanned, a count is output for each + of them and the -t option can be used to cause a total to be + output at the end. However, if the --files-with-matches op- + tion is also used, only those files whose counts are greater than zero are listed. When -c is used, the -A, -B, and -C op- tions are ignored. --colour, --color If this option is given without any data, it is equivalent to - "--colour=auto". If data is required, it must be given in + "--colour=auto". If data is required, it must be given in the same shell item, separated by an equals sign. --colour=value, --color=value This option specifies under what circumstances the parts of a line that matched a pattern should be coloured in the output. - By default, the output is not coloured. The value (which is - optional, see above) may be "never", "always", or "auto". In - the latter case, colouring happens only if the standard out- - put is connected to a terminal. More resources are used when + By default, the output is not coloured. The value (which is + optional, see above) may be "never", "always", or "auto". In + the latter case, colouring happens only if the standard out- + put is connected to a terminal. More resources are used when colouring is enabled, because pcre2grep has to search for all - possible matches in a line, not just one, in order to colour + possible matches in a line, not just one, in order to colour them all. - The colour that is used can be specified by setting one of - the environment variables PCRE2GREP_COLOUR, PCRE2GREP_COLOR, + The colour that is used can be specified by setting one of + the environment variables PCRE2GREP_COLOUR, PCRE2GREP_COLOR, PCREGREP_COLOUR, or PCREGREP_COLOR, which are checked in that order. If none of these are set, pcre2grep looks for - GREP_COLORS or GREP_COLOR (in that order). The value of the - variable should be a string of two numbers, separated by a - semicolon, except in the case of GREP_COLORS, which must + GREP_COLORS or GREP_COLOR (in that order). The value of the + variable should be a string of two numbers, separated by a + semicolon, except in the case of GREP_COLORS, which must start with "ms=" or "mt=" followed by two semicolon-separated - colours, terminated by the end of the string or by a colon. - If GREP_COLORS does not start with "ms=" or "mt=" it is ig- + colours, terminated by the end of the string or by a colon. + If GREP_COLORS does not start with "ms=" or "mt=" it is ig- nored, and GREP_COLOR is checked. - If the string obtained from one of the above variables con- + If the string obtained from one of the above variables con- tains any characters other than semicolon or digits, the set- ting is ignored and the default colour is used. The string is copied directly into the control string for setting colour on - a terminal, so it is your responsibility to ensure that the - values make sense. If no relevant environment variable is + a terminal, so it is your responsibility to ensure that the + values make sense. If no relevant environment variable is set, the default is "1;31", which gives red. -D action, --devices=action - If an input path is not a regular file or a directory, "ac- - tion" specifies how it is to be processed. Valid values are + If an input path is not a regular file or a directory, "ac- + tion" specifies how it is to be processed. Valid values are "read" (the default) or "skip" (silently skip the path). -d action, --directories=action If an input path is a directory, "action" specifies how it is - to be processed. Valid values are "read" (the default in - non-Windows environments, for compatibility with GNU grep), - "recurse" (equivalent to the -r option), or "skip" (silently - skip the path, the default in Windows environments). In the - "read" case, directories are read as if they were ordinary - files. In some operating systems the effect of reading a di- - rectory like this is an immediate end-of-file; in others it + to be processed. Valid values are "read" (the default in + non-Windows environments, for compatibility with GNU grep), + "recurse" (equivalent to the -r option), or "skip" (silently + skip the path, the default in Windows environments). In the + "read" case, directories are read as if they were ordinary + files. In some operating systems the effect of reading a di- + rectory like this is an immediate end-of-file; in others it may provoke an error. --depth-limit=number @@ -270,199 +276,199 @@ OPTIONS -e pattern, --regex=pattern, --regexp=pattern Specify a pattern to be matched. This option can be used mul- tiple times in order to specify several patterns. It can also - be used as a way of specifying a single pattern that starts - with a hyphen. When -e is used, no argument pattern is taken - from the command line; all arguments are treated as file - names. There is no limit to the number of patterns. They are - applied to each line in the order in which they are defined + be used as a way of specifying a single pattern that starts + with a hyphen. When -e is used, no argument pattern is taken + from the command line; all arguments are treated as file + names. There is no limit to the number of patterns. They are + applied to each line in the order in which they are defined until one matches. - If -f is used with -e, the command line patterns are matched + If -f is used with -e, the command line patterns are matched first, followed by the patterns from the file(s), independent - of the order in which these options are specified. Note that - multiple use of -e is not the same as a single pattern with + of the order in which these options are specified. Note that + multiple use of -e is not the same as a single pattern with alternatives. For example, X|Y finds the first character in a - line that is X or Y, whereas if the two patterns are given + line that is X or Y, whereas if the two patterns are given separately, with X first, pcre2grep finds X if it is present, even if it follows Y in the line. It finds Y only if there is - no X in the line. This matters only if you are using -o or + no X in the line. This matters only if you are using -o or --colo(u)r to show the part(s) of the line that matched. --exclude=pattern Files (but not directories) whose names match the pattern are - skipped without being processed. This applies to all files, - whether listed on the command line, obtained from --file- + skipped without being processed. This applies to all files, + whether listed on the command line, obtained from --file- list, or by scanning a directory. The pattern is a PCRE2 reg- - ular expression, and is matched against the final component + ular expression, and is matched against the final component of the file name, not the entire path. The -F, -w, and -x op- - tions do not apply to this pattern. The option may be given + tions do not apply to this pattern. The option may be given any number of times in order to specify multiple patterns. If - a file name matches both an --include and an --exclude pat- + a file name matches both an --include and an --exclude pat- tern, it is excluded. There is no short form for this option. --exclude-from=filename - Treat each non-empty line of the file as the data for an + Treat each non-empty line of the file as the data for an --exclude option. What constitutes a newline when reading the - file is the operating system's default. The --newline option - has no effect on this option. This option may be given more + file is the operating system's default. The --newline option + has no effect on this option. This option may be given more than once in order to specify a number of files to read. --exclude-dir=pattern Directories whose names match the pattern are skipped without - being processed, whatever the setting of the --recursive op- - tion. This applies to all directories, whether listed on the - command line, obtained from --file-list, or by scanning a - parent directory. The pattern is a PCRE2 regular expression, - and is matched against the final component of the directory - name, not the entire path. The -F, -w, and -x options do not - apply to this pattern. The option may be given any number of - times in order to specify more than one pattern. If a direc- - tory matches both --include-dir and --exclude-dir, it is ex- + being processed, whatever the setting of the --recursive op- + tion. This applies to all directories, whether listed on the + command line, obtained from --file-list, or by scanning a + parent directory. The pattern is a PCRE2 regular expression, + and is matched against the final component of the directory + name, not the entire path. The -F, -w, and -x options do not + apply to this pattern. The option may be given any number of + times in order to specify more than one pattern. If a direc- + tory matches both --include-dir and --exclude-dir, it is ex- cluded. There is no short form for this option. -F, --fixed-strings - Interpret each data-matching pattern as a list of fixed - strings, separated by newlines, instead of as a regular ex- + Interpret each data-matching pattern as a list of fixed + strings, separated by newlines, instead of as a regular ex- pression. What constitutes a newline for this purpose is con- trolled by the --newline option. The -w (match as a word) and - -x (match whole line) options can be used with -F. They ap- - ply to each of the fixed strings. A line is selected if any + -x (match whole line) options can be used with -F. They ap- + ply to each of the fixed strings. A line is selected if any of the fixed strings are found in it (subject to -w or -x, if - present). This option applies only to the patterns that are - matched against the contents of files; it does not apply to - patterns specified by any of the --include or --exclude op- + present). This option applies only to the patterns that are + matched against the contents of files; it does not apply to + patterns specified by any of the --include or --exclude op- tions. -f filename, --file=filename - Read patterns from the file, one per line, and match them - against each line of input. As is the case with patterns on - the command line, no delimiters should be used. What consti- - tutes a newline when reading the file is the operating sys- - tem's default interpretation of \n. The --newline option has - no effect on this option. Trailing white space is removed - from each line, and blank lines are ignored. An empty file - contains no patterns and therefore matches nothing. Patterns - read from a file in this way may contain binary zeros, which - are treated as ordinary data characters. See also the com- - ments about multiple patterns versus a single pattern with + Read patterns from the file, one per line, and match them + against each line of input. As is the case with patterns on + the command line, no delimiters should be used. What consti- + tutes a newline when reading the file is the operating sys- + tem's default interpretation of \n. The --newline option has + no effect on this option. Trailing white space is removed + from each line, and blank lines are ignored. An empty file + contains no patterns and therefore matches nothing. Patterns + read from a file in this way may contain binary zeros, which + are treated as ordinary data characters. See also the com- + ments about multiple patterns versus a single pattern with alternatives in the description of -e above. - If this option is given more than once, all the specified - files are read. A data line is output if any of the patterns - match it. A file name can be given as "-" to refer to the - standard input. When -f is used, patterns specified on the - command line using -e may also be present; they are tested - before the file's patterns. However, no other pattern is + If this option is given more than once, all the specified + files are read. A data line is output if any of the patterns + match it. A file name can be given as "-" to refer to the + standard input. When -f is used, patterns specified on the + command line using -e may also be present; they are tested + before the file's patterns. However, no other pattern is taken from the command line; all arguments are treated as the names of paths to be searched. --file-list=filename - Read a list of files and/or directories that are to be + Read a list of files and/or directories that are to be scanned from the given file, one per line. What constitutes a - newline when reading the file is the operating system's de- - fault. Trailing white space is removed from each line, and + newline when reading the file is the operating system's de- + fault. Trailing white space is removed from each line, and blank lines are ignored. These paths are processed before any - that are listed on the command line. The file name can be - given as "-" to refer to the standard input. If --file and - --file-list are both specified as "-", patterns are read - first. This is useful only when the standard input is a ter- - minal, from which further lines (the list of files) can be + that are listed on the command line. The file name can be + given as "-" to refer to the standard input. If --file and + --file-list are both specified as "-", patterns are read + first. This is useful only when the standard input is a ter- + minal, from which further lines (the list of files) can be read after an end-of-file indication. If this option is given more than once, all the specified files are read. --file-offsets - Instead of showing lines or parts of lines that match, show - each match as an offset from the start of the file and a - length, separated by a comma. In this mode, no context is - shown. That is, the -A, -B, and -C options are ignored. If + Instead of showing lines or parts of lines that match, show + each match as an offset from the start of the file and a + length, separated by a comma. In this mode, no context is + shown. That is, the -A, -B, and -C options are ignored. If there is more than one match in a line, each of them is shown - separately. This option is mutually exclusive with --output, + separately. This option is mutually exclusive with --output, --line-offsets, and --only-matching. -H, --with-filename - Force the inclusion of the file name at the start of output + Force the inclusion of the file name at the start of output lines when searching a single file. By default, the file name is not shown in this case. For matching lines, the file name is followed by a colon; for context lines, a hyphen separator - is used. If a line number is also being output, it follows - the file name. When the -M option causes a pattern to match - more than one line, only the first is preceded by the file - name. This option overrides any previous -h, -l, or -L op- + is used. If a line number is also being output, it follows + the file name. When the -M option causes a pattern to match + more than one line, only the first is preceded by the file + name. This option overrides any previous -h, -l, or -L op- tions. -h, --no-filename Suppress the output file names when searching multiple files. - By default, file names are shown when multiple files are - searched. For matching lines, the file name is followed by a - colon; for context lines, a hyphen separator is used. If a - line number is also being output, it follows the file name. + By default, file names are shown when multiple files are + searched. For matching lines, the file name is followed by a + colon; for context lines, a hyphen separator is used. If a + line number is also being output, it follows the file name. This option overrides any previous -H, -L, or -l options. --heap-limit=number See --match-limit below. - --help Output a help message, giving brief details of the command - options and file type support, and then exit. Anything else + --help Output a help message, giving brief details of the command + options and file type support, and then exit. Anything else on the command line is ignored. - -I Ignore binary files. This is equivalent to --binary- + -I Ignore binary files. This is equivalent to --binary- files=without-match. -i, --ignore-case Ignore upper/lower case distinctions during comparisons. --include=pattern - If any --include patterns are specified, the only files that + If any --include patterns are specified, the only files that are processed are those whose names match one of the patterns - and do not match an --exclude pattern. This option does not - affect directories, but it applies to all files, whether - listed on the command line, obtained from --file-list, or by - scanning a directory. The pattern is a PCRE2 regular expres- - sion, and is matched against the final component of the file - name, not the entire path. The -F, -w, and -x options do not - apply to this pattern. The option may be given any number of - times. If a file name matches both an --include and an --ex- - clude pattern, it is excluded. There is no short form for + and do not match an --exclude pattern. This option does not + affect directories, but it applies to all files, whether + listed on the command line, obtained from --file-list, or by + scanning a directory. The pattern is a PCRE2 regular expres- + sion, and is matched against the final component of the file + name, not the entire path. The -F, -w, and -x options do not + apply to this pattern. The option may be given any number of + times. If a file name matches both an --include and an --ex- + clude pattern, it is excluded. There is no short form for this option. --include-from=filename - Treat each non-empty line of the file as the data for an + Treat each non-empty line of the file as the data for an --include option. What constitutes a newline for this purpose - is the operating system's default. The --newline option has + is the operating system's default. The --newline option has no effect on this option. This option may be given any number of times; all the files are read. --include-dir=pattern - If any --include-dir patterns are specified, the only direc- - tories that are processed are those whose names match one of - the patterns and do not match an --exclude-dir pattern. This - applies to all directories, whether listed on the command - line, obtained from --file-list, or by scanning a parent di- - rectory. The pattern is a PCRE2 regular expression, and is - matched against the final component of the directory name, - not the entire path. The -F, -w, and -x options do not apply + If any --include-dir patterns are specified, the only direc- + tories that are processed are those whose names match one of + the patterns and do not match an --exclude-dir pattern. This + applies to all directories, whether listed on the command + line, obtained from --file-list, or by scanning a parent di- + rectory. The pattern is a PCRE2 regular expression, and is + matched against the final component of the directory name, + not the entire path. The -F, -w, and -x options do not apply to this pattern. The option may be given any number of times. - If a directory matches both --include-dir and --exclude-dir, + If a directory matches both --include-dir and --exclude-dir, it is excluded. There is no short form for this option. -L, --files-without-match - Instead of outputting lines from the files, just output the - names of the files that do not contain any lines that would - have been output. Each file name is output once, on a sepa- - rate line. This option overrides any previous -H, -h, or -l + Instead of outputting lines from the files, just output the + names of the files that do not contain any lines that would + have been output. Each file name is output once, on a sepa- + rate line. This option overrides any previous -H, -h, or -l options. -l, --files-with-matches - Instead of outputting lines from the files, just output the + Instead of outputting lines from the files, just output the names of the files containing lines that would have been out- - put. Each file name is output once, on a separate line. - Searching normally stops as soon as a matching line is found - in a file. However, if the -c (count) option is also used, - matching continues in order to obtain the correct count, and - those files that have at least one match are listed along + put. Each file name is output once, on a separate line. + Searching normally stops as soon as a matching line is found + in a file. However, if the -c (count) option is also used, + matching continues in order to obtain the correct count, and + those files that have at least one match are listed along with their counts. Using this option with -c is a way of sup- - pressing the listing of files with no matches that occurs - with -c on its own. This option overrides any previous -H, + pressing the listing of files with no matches that occurs + with -c on its own. This option overrides any previous -H, -h, or -L options. --label=name @@ -471,123 +477,123 @@ OPTIONS input)" is used. There is no short form for this option. --line-buffered - When this option is given, non-compressed input is read and - processed line by line, and the output is flushed after each - write. By default, input is read in large chunks, unless - pcre2grep can determine that it is reading from a terminal, + When this option is given, non-compressed input is read and + processed line by line, and the output is flushed after each + write. By default, input is read in large chunks, unless + pcre2grep can determine that it is reading from a terminal, which is currently possible only in Unix-like environments or Windows. Output to terminal is normally automatically flushed - by the operating system. This option can be useful when the - input or output is attached to a pipe and you do not want - pcre2grep to buffer up large amounts of data. However, its - use will affect performance, and the -M (multiline) option - ceases to work. When input is from a compressed .gz or .bz2 + by the operating system. This option can be useful when the + input or output is attached to a pipe and you do not want + pcre2grep to buffer up large amounts of data. However, its + use will affect performance, and the -M (multiline) option + ceases to work. When input is from a compressed .gz or .bz2 file, --line-buffered is ignored. --line-offsets - Instead of showing lines or parts of lines that match, show + Instead of showing lines or parts of lines that match, show each match as a line number, the offset from the start of the - line, and a length. The line number is terminated by a colon - (as usual; see the -n option), and the offset and length are - separated by a comma. In this mode, no context is shown. - That is, the -A, -B, and -C options are ignored. If there is - more than one match in a line, each of them is shown sepa- - rately. This option is mutually exclusive with --output, + line, and a length. The line number is terminated by a colon + (as usual; see the -n option), and the offset and length are + separated by a comma. In this mode, no context is shown. + That is, the -A, -B, and -C options are ignored. If there is + more than one match in a line, each of them is shown sepa- + rately. This option is mutually exclusive with --output, --file-offsets, and --only-matching. --locale=locale-name - This option specifies a locale to be used for pattern match- - ing. It overrides the value in the LC_ALL or LC_CTYPE envi- - ronment variables. If no locale is specified, the PCRE2 li- + This option specifies a locale to be used for pattern match- + ing. It overrides the value in the LC_ALL or LC_CTYPE envi- + ronment variables. If no locale is specified, the PCRE2 li- brary's default (usually the "C" locale) is used. There is no short form for this option. -M, --multiline - Allow patterns to match more than one line. When this option + Allow patterns to match more than one line. When this option is set, the PCRE2 library is called in "multiline" mode. This - allows a matched string to extend past the end of a line and - continue on one or more subsequent lines. Patterns used with + allows a matched string to extend past the end of a line and + continue on one or more subsequent lines. Patterns used with -M may usefully contain literal newline characters and inter- - nal occurrences of ^ and $ characters. The output for a suc- - cessful match may consist of more than one line. The first - line is the line in which the match started, and the last - line is the line in which the match ended. If the matched - string ends with a newline sequence, the output ends at the - end of that line. If -v is set, none of the lines in a - multi-line match are output. Once a match has been handled, - scanning restarts at the beginning of the line after the one + nal occurrences of ^ and $ characters. The output for a suc- + cessful match may consist of more than one line. The first + line is the line in which the match started, and the last + line is the line in which the match ended. If the matched + string ends with a newline sequence, the output ends at the + end of that line. If -v is set, none of the lines in a + multi-line match are output. Once a match has been handled, + scanning restarts at the beginning of the line after the one in which the match ended. - The newline sequence that separates multiple lines must be - matched as part of the pattern. For example, to find the - phrase "regular expression" in a file where "regular" might - be at the end of a line and "expression" at the start of the + The newline sequence that separates multiple lines must be + matched as part of the pattern. For example, to find the + phrase "regular expression" in a file where "regular" might + be at the end of a line and "expression" at the start of the next line, you could use this command: pcre2grep -M 'regular\s+expression' The \s escape sequence matches any white space character, in- - cluding newlines, and is followed by + so as to match trail- - ing white space on the first line as well as possibly han- + cluding newlines, and is followed by + so as to match trail- + ing white space on the first line as well as possibly han- dling a two-character newline sequence. - There is a limit to the number of lines that can be matched, - imposed by the way that pcre2grep buffers the input file as - it scans it. With a sufficiently large processing buffer, + There is a limit to the number of lines that can be matched, + imposed by the way that pcre2grep buffers the input file as + it scans it. With a sufficiently large processing buffer, this should not be a problem, but the -M option does not work when input is read line by line (see --line-buffered.) -m number, --max-count=number - Stop processing after finding number matching lines, or non- - matching lines if -v is also set. Any trailing context lines - are output after the final match. In multiline mode, each - multiline match counts as just one line for this purpose. If - this limit is reached when reading the standard input from a + Stop processing after finding number matching lines, or non- + matching lines if -v is also set. Any trailing context lines + are output after the final match. In multiline mode, each + multiline match counts as just one line for this purpose. If + this limit is reached when reading the standard input from a regular file, the file is left positioned just after the last - matching line. If -c is also set, the count that is output - is never greater than number. This option has no effect if + matching line. If -c is also set, the count that is output + is never greater than number. This option has no effect if used with -L, -l, or -q, or when just checking for a match in a binary file. --match-limit=number - Processing some regular expression patterns may take a very + Processing some regular expression patterns may take a very long time to search for all possible matching strings. Others - may require a very large amount of memory. There are three + may require a very large amount of memory. There are three options that set resource limits for matching. The --match-limit option provides a means of limiting comput- - ing resource usage when processing patterns that are not go- + ing resource usage when processing patterns that are not go- ing to match, but which have a very large number of possibil- ities in their search trees. The classic example is a pattern - that uses nested unlimited repeats. Internally, PCRE2 has a - counter that is incremented each time around its main pro- - cessing loop. If the value set by --match-limit is reached, + that uses nested unlimited repeats. Internally, PCRE2 has a + counter that is incremented each time around its main pro- + cessing loop. If the value set by --match-limit is reached, an error occurs. - The --heap-limit option specifies, as a number of kibibytes - (units of 1024 bytes), the amount of heap memory that may be + The --heap-limit option specifies, as a number of kibibytes + (units of 1024 bytes), the amount of heap memory that may be used for matching. Heap memory is needed only if matching the - pattern requires a significant number of nested backtracking + pattern requires a significant number of nested backtracking points to be remembered. This parameter can be set to zero to forbid the use of heap memory altogether. - The --depth-limit option limits the depth of nested back- + The --depth-limit option limits the depth of nested back- tracking points, which indirectly limits the amount of memory that is used. The amount of memory needed for each backtrack- - ing point depends on the number of capturing parentheses in + ing point depends on the number of capturing parentheses in the pattern, so the amount of memory that is used before this - limit acts varies from pattern to pattern. This limit is of + limit acts varies from pattern to pattern. This limit is of use only if it is set smaller than --match-limit. - There are no short forms for these options. The default lim- - its can be set when the PCRE2 library is compiled; if they - are not specified, the defaults are very large and so effec- + There are no short forms for these options. The default lim- + its can be set when the PCRE2 library is compiled; if they + are not specified, the defaults are very large and so effec- tively unlimited. --max-buffer-size=number - This limits the expansion of the processing buffer, whose - initial size can be set by --buffer-size. The maximum buffer - size is silently forced to be no smaller than the starting + This limits the expansion of the processing buffer, whose + initial size can be set by --buffer-size. The maximum buffer + size is silently forced to be no smaller than the starting buffer size. -N newline-type, --newline=newline-type @@ -596,55 +602,55 @@ OPTIONS pcre2grep -N CRLF 'some pattern' - The newline type may be specified in upper, lower, or mixed - case. If the newline type is NUL, lines are separated by bi- - nary zero characters. The other types are the single-charac- - ter sequences CR (carriage return) and LF (linefeed), the - two-character sequence CRLF, an "anycrlf" type, which recog- - nizes any of the preceding three types, and an "any" type, - for which any Unicode line ending sequence is assumed to end - a line. The Unicode sequences are the three just mentioned, - plus VT (vertical tab, U+000B), FF (form feed, U+000C), NEL - (next line, U+0085), LS (line separator, U+2028), and PS + The newline type may be specified in upper, lower, or mixed + case. If the newline type is NUL, lines are separated by bi- + nary zero characters. The other types are the single-charac- + ter sequences CR (carriage return) and LF (linefeed), the + two-character sequence CRLF, an "anycrlf" type, which recog- + nizes any of the preceding three types, and an "any" type, + for which any Unicode line ending sequence is assumed to end + a line. The Unicode sequences are the three just mentioned, + plus VT (vertical tab, U+000B), FF (form feed, U+000C), NEL + (next line, U+0085), LS (line separator, U+2028), and PS (paragraph separator, U+2029). - When the PCRE2 library is built, a default line-ending se- - quence is specified. This is normally the standard sequence - for the operating system. Unless otherwise specified by this + When the PCRE2 library is built, a default line-ending se- + quence is specified. This is normally the standard sequence + for the operating system. Unless otherwise specified by this option, pcre2grep uses the library's default. - This option makes it possible to use pcre2grep to scan files + This option makes it possible to use pcre2grep to scan files that have come from other environments without having to mod- - ify their line endings. If the data that is being scanned - does not agree with the convention set by this option, - pcre2grep may behave in strange ways. Note that this option - does not apply to files specified by the -f, --exclude-from, - or --include-from options, which are expected to use the op- + ify their line endings. If the data that is being scanned + does not agree with the convention set by this option, + pcre2grep may behave in strange ways. Note that this option + does not apply to files specified by the -f, --exclude-from, + or --include-from options, which are expected to use the op- erating system's standard newline sequence. -n, --line-number Precede each output line by its line number in the file, fol- - lowed by a colon for matching lines or a hyphen for context + lowed by a colon for matching lines or a hyphen for context lines. If the file name is also being output, it precedes the - line number. When the -M option causes a pattern to match - more than one line, only the first is preceded by its line + line number. When the -M option causes a pattern to match + more than one line, only the first is preceded by its line number. This option is forced if --line-offsets is used. - --no-jit If the PCRE2 library is built with support for just-in-time + --no-jit If the PCRE2 library is built with support for just-in-time compiling (which speeds up matching), pcre2grep automatically makes use of this, unless it was explicitly disabled at build - time. This option can be used to disable the use of JIT at - run time. It is provided for testing and working round prob- + time. This option can be used to disable the use of JIT at + run time. It is provided for testing and working round prob- lems. It should never be needed in normal use. -O text, --output=text - When there is a match, instead of outputting the line that - matched, output just the text specified in this option, fol- - lowed by an operating-system standard newline. In this mode, - no context is shown. That is, the -A, -B, and -C options are - ignored. The --newline option has no effect on this option, + When there is a match, instead of outputting the line that + matched, output just the text specified in this option, fol- + lowed by an operating-system standard newline. In this mode, + no context is shown. That is, the -A, -B, and -C options are + ignored. The --newline option has no effect on this option, which is mutually exclusive with --only-matching, --file-off- - sets, and --line-offsets. However, like --only-matching, if + sets, and --line-offsets. However, like --only-matching, if there is more than one match in a line, each of them causes a line of output. @@ -652,158 +658,158 @@ OPTIONS to insert the contents of the matched part of the line and/or captured substrings into the text. - $ or ${} is replaced by the captured sub- - string of the given decimal number; zero substitutes the + $ or ${} is replaced by the captured sub- + string of the given decimal number; zero substitutes the whole match. If the number is greater than the number of cap- - turing substrings, or if the capture is unset, the replace- + turing substrings, or if the capture is unset, the replace- ment is empty. - $a is replaced by bell; $b by backspace; $e by escape; $f by - form feed; $n by newline; $r by carriage return; $t by tab; + $a is replaced by bell; $b by backspace; $e by escape; $f by + form feed; $n by newline; $r by carriage return; $t by tab; $v by vertical tab. $o or $o{} is replaced by the character whose - code point is the given octal number. In the first form, up - to three octal digits are processed. When more digits are - needed in Unicode mode to specify a wide character, the sec- + code point is the given octal number. In the first form, up + to three octal digits are processed. When more digits are + needed in Unicode mode to specify a wide character, the sec- ond form must be used. - $x or $x{} is replaced by the character rep- - resented by the given hexadecimal number. In the first form, - up to two hexadecimal digits are processed. When more digits - are needed in Unicode mode to specify a wide character, the + $x or $x{} is replaced by the character rep- + resented by the given hexadecimal number. In the first form, + up to two hexadecimal digits are processed. When more digits + are needed in Unicode mode to specify a wide character, the second form must be used. - Any other character is substituted by itself. In particular, + Any other character is substituted by itself. In particular, $$ is replaced by a single dollar. -o, --only-matching Show only the part of the line that matched a pattern instead - of the whole line. In this mode, no context is shown. That - is, the -A, -B, and -C options are ignored. If there is more - than one match in a line, each of them is shown separately, - on a separate line of output. If -o is combined with -v (in- - vert the sense of the match to find non-matching lines), no - output is generated, but the return code is set appropri- - ately. If the matched portion of the line is empty, nothing - is output unless the file name or line number are being - printed, in which case they are shown on an otherwise empty + of the whole line. In this mode, no context is shown. That + is, the -A, -B, and -C options are ignored. If there is more + than one match in a line, each of them is shown separately, + on a separate line of output. If -o is combined with -v (in- + vert the sense of the match to find non-matching lines), no + output is generated, but the return code is set appropri- + ately. If the matched portion of the line is empty, nothing + is output unless the file name or line number are being + printed, in which case they are shown on an otherwise empty line. This option is mutually exclusive with --output, --file-offsets and --line-offsets. -onumber, --only-matching=number - Show only the part of the line that matched the capturing + Show only the part of the line that matched the capturing parentheses of the given number. Up to 50 capturing parenthe- - ses are supported by default. This limit can be changed via - the --om-capture option. A pattern may contain any number of - capturing parentheses, but only those whose number is within - the limit can be accessed by -o. An error occurs if the num- + ses are supported by default. This limit can be changed via + the --om-capture option. A pattern may contain any number of + capturing parentheses, but only those whose number is within + the limit can be accessed by -o. An error occurs if the num- ber specified by -o is greater than the limit. -o0 is the same as -o without a number. Because these options - can be given without an argument (see above), if an argument - is present, it must be given in the same shell item, for ex- - ample, -o3 or --only-matching=2. The comments given for the - non-argument case above also apply to this option. If the - specified capturing parentheses do not exist in the pattern, - or were not set in the match, nothing is output unless the + can be given without an argument (see above), if an argument + is present, it must be given in the same shell item, for ex- + ample, -o3 or --only-matching=2. The comments given for the + non-argument case above also apply to this option. If the + specified capturing parentheses do not exist in the pattern, + or were not set in the match, nothing is output unless the file name or line number are being output. - If this option is given multiple times, multiple substrings - are output for each match, in the order the options are - given, and all on one line. For example, -o3 -o1 -o3 causes - the substrings matched by capturing parentheses 3 and 1 and - then 3 again to be output. By default, there is no separator + If this option is given multiple times, multiple substrings + are output for each match, in the order the options are + given, and all on one line. For example, -o3 -o1 -o3 causes + the substrings matched by capturing parentheses 3 and 1 and + then 3 again to be output. By default, there is no separator (but see the next but one option). --om-capture=number - Set the number of capturing parentheses that can be accessed + Set the number of capturing parentheses that can be accessed by -o. The default is 50. --om-separator=text - Specify a separating string for multiple occurrences of -o. - The default is an empty string. Separating strings are never + Specify a separating string for multiple occurrences of -o. + The default is an empty string. Separating strings are never coloured. -q, --quiet Work quietly, that is, display nothing except error messages. - The exit status indicates whether or not any matches were + The exit status indicates whether or not any matches were found. -r, --recursive - If any given path is a directory, recursively scan the files - it contains, taking note of any --include and --exclude set- - tings. By default, a directory is read as a normal file; in - some operating systems this gives an immediate end-of-file. - This option is a shorthand for setting the -d option to "re- + If any given path is a directory, recursively scan the files + it contains, taking note of any --include and --exclude set- + tings. By default, a directory is read as a normal file; in + some operating systems this gives an immediate end-of-file. + This option is a shorthand for setting the -d option to "re- curse". --recursion-limit=number - This is an obsolete synonym for --depth-limit. See --match- + This is an obsolete synonym for --depth-limit. See --match- limit above for details. -s, --no-messages - Suppress error messages about non-existent or unreadable - files. Such files are quietly skipped. However, the return + Suppress error messages about non-existent or unreadable + files. Such files are quietly skipped. However, the return code is still 2, even if matches were found in other files. -t, --total-count - This option is useful when scanning more than one file. If - used on its own, -t suppresses all output except for a grand - total number of matching lines (or non-matching lines if -v + This option is useful when scanning more than one file. If + used on its own, -t suppresses all output except for a grand + total number of matching lines (or non-matching lines if -v is used) in all the files. If -t is used with -c, a grand to- - tal is output except when the previous output is just one - line. In other words, it is not output when just one file's - count is listed. If file names are being output, the grand - total is preceded by "TOTAL:". Otherwise, it appears as just - another number. The -t option is ignored when used with -L - (list files without matches), because the grand total would + tal is output except when the previous output is just one + line. In other words, it is not output when just one file's + count is listed. If file names are being output, the grand + total is preceded by "TOTAL:". Otherwise, it appears as just + another number. The -t option is ignored when used with -L + (list files without matches), because the grand total would always be zero. -u, --utf Operate in UTF-8 mode. This option is available only if PCRE2 has been compiled with UTF-8 support. All patterns (including - those for any --exclude and --include options) and all lines - that are scanned must be valid strings of UTF-8 characters. + those for any --exclude and --include options) and all lines + that are scanned must be valid strings of UTF-8 characters. If an invalid UTF-8 string is encountered, an error occurs. -U, --utf-allow-invalid - As --utf, but in addition subject lines may contain invalid - UTF-8 code unit sequences. These can never form part of any - pattern match. Patterns themselves, however, must still be + As --utf, but in addition subject lines may contain invalid + UTF-8 code unit sequences. These can never form part of any + pattern match. Patterns themselves, however, must still be valid UTF-8 strings. This facility allows valid UTF-8 strings to be sought within arbitrary byte sequences in executable or - other binary files. For more details about matching in non- + other binary files. For more details about matching in non- valid UTF-8 strings, see the pcre2unicode(3) documentation. -V, --version - Write the version numbers of pcre2grep and the PCRE2 library - to the standard output and then exit. Anything else on the + Write the version numbers of pcre2grep and the PCRE2 library + to the standard output and then exit. Anything else on the command line is ignored. -v, --invert-match - Invert the sense of the match, so that lines which do not - match any of the patterns are the ones that are found. When - this option is set, options such as --only-matching and - --output, which specify parts of a match that are to be out- + Invert the sense of the match, so that lines which do not + match any of the patterns are the ones that are found. When + this option is set, options such as --only-matching and + --output, which specify parts of a match that are to be out- put, are ignored. -w, --word-regex, --word-regexp Force the patterns only to match "words". That is, there must - be a word boundary at the start and end of each matched - string. This is equivalent to having "\b(?:" at the start of - each pattern, and ")\b" at the end. This option applies only - to the patterns that are matched against the contents of - files; it does not apply to patterns specified by any of the + be a word boundary at the start and end of each matched + string. This is equivalent to having "\b(?:" at the start of + each pattern, and ")\b" at the end. This option applies only + to the patterns that are matched against the contents of + files; it does not apply to patterns specified by any of the --include or --exclude options. -x, --line-regex, --line-regexp - Force the patterns to start matching only at the beginnings - of lines, and in addition, require them to match entire + Force the patterns to start matching only at the beginnings + of lines, and in addition, require them to match entire lines. In multiline mode the match may be more than one line. This is equivalent to having "^(?:" at the start of each pat- - tern and ")$" at the end. This option applies only to the - patterns that are matched against the contents of files; it - does not apply to patterns specified by any of the --include + tern and ")$" at the end. This option applies only to the + patterns that are matched against the contents of files; it + does not apply to patterns specified by any of the --include or --exclude options. @@ -817,137 +823,137 @@ ENVIRONMENT VARIABLES NEWLINES - The -N (--newline) option allows pcre2grep to scan files with newline - conventions that differ from the default. This option affects only the - way scanned files are processed. It does not affect the interpretation - of files specified by the -f, --file-list, --exclude-from, or --in- + The -N (--newline) option allows pcre2grep to scan files with newline + conventions that differ from the default. This option affects only the + way scanned files are processed. It does not affect the interpretation + of files specified by the -f, --file-list, --exclude-from, or --in- clude-from options. - Any parts of the scanned input files that are written to the standard - output are copied with whatever newline sequences they have in the in- - put. However, if the final line of a file is output, and it does not - end with a newline sequence, a newline sequence is added. If the new- - line setting is CR, LF, CRLF or NUL, that line ending is output; for + Any parts of the scanned input files that are written to the standard + output are copied with whatever newline sequences they have in the in- + put. However, if the final line of a file is output, and it does not + end with a newline sequence, a newline sequence is added. If the new- + line setting is CR, LF, CRLF or NUL, that line ending is output; for the other settings (ANYCRLF or ANY) a single NL is used. - The newline setting does not affect the way in which pcre2grep writes - newlines in informational messages to the standard output and error - streams. Under Windows, the standard output is set to be binary, so - that "\r\n" at the ends of output lines that are copied from the input - is not converted to "\r\r\n" by the C I/O library. This means that any - messages written to the standard output must end with "\r\n". For all - other operating systems, and for all messages to the standard error + The newline setting does not affect the way in which pcre2grep writes + newlines in informational messages to the standard output and error + streams. Under Windows, the standard output is set to be binary, so + that "\r\n" at the ends of output lines that are copied from the input + is not converted to "\r\r\n" by the C I/O library. This means that any + messages written to the standard output must end with "\r\n". For all + other operating systems, and for all messages to the standard error stream, "\n" is used. OPTIONS COMPATIBILITY Many of the short and long forms of pcre2grep's options are the same as - in the GNU grep program. Any long option of the form --xxx-regexp (GNU + in the GNU grep program. Any long option of the form --xxx-regexp (GNU terminology) is also available as --xxx-regex (PCRE2 terminology). How- - ever, the --depth-limit, --file-list, --file-offsets, --heap-limit, - --include-dir, --line-offsets, --locale, --match-limit, -M, --multi- - line, -N, --newline, --om-separator, --output, -u, --utf, -U, and + ever, the --depth-limit, --file-list, --file-offsets, --heap-limit, + --include-dir, --line-offsets, --locale, --match-limit, -M, --multi- + line, -N, --newline, --om-separator, --output, -u, --utf, -U, and --utf-allow-invalid options are specific to pcre2grep, as is the use of the --only-matching option with a capturing parentheses number. - Although most of the common options work the same way, a few are dif- - ferent in pcre2grep. For example, the --include option's argument is a - glob for GNU grep, but a regular expression for pcre2grep. If both the - -c and -l options are given, GNU grep lists only file names, without + Although most of the common options work the same way, a few are dif- + ferent in pcre2grep. For example, the --include option's argument is a + glob for GNU grep, but a regular expression for pcre2grep. If both the + -c and -l options are given, GNU grep lists only file names, without counts, but pcre2grep gives the counts as well. OPTIONS WITH DATA There are four different ways in which an option with data can be spec- - ified. If a short form option is used, the data may follow immedi- + ified. If a short form option is used, the data may follow immedi- ately, or (with one exception) in the next command line item. For exam- ple: -f/some/file -f /some/file - The exception is the -o option, which may appear with or without data. - Because of this, if data is present, it must follow immediately in the + The exception is the -o option, which may appear with or without data. + Because of this, if data is present, it must follow immediately in the same item, for example -o3. - If a long form option is used, the data may appear in the same command - line item, separated by an equals character, or (with two exceptions) + If a long form option is used, the data may appear in the same command + line item, separated by an equals character, or (with two exceptions) it may appear in the next command line item. For example: --file=/some/file --file /some/file - Note, however, that if you want to supply a file name beginning with ~ - as data in a shell command, and have the shell expand ~ to a home di- - rectory, you must separate the file name from the option, because the + Note, however, that if you want to supply a file name beginning with ~ + as data in a shell command, and have the shell expand ~ to a home di- + rectory, you must separate the file name from the option, because the shell does not treat ~ specially unless it is at the start of an item. - The exceptions to the above are the --colour (or --color) and --only- - matching options, for which the data is optional. If one of these op- - tions does have data, it must be given in the first form, using an + The exceptions to the above are the --colour (or --color) and --only- + matching options, for which the data is optional. If one of these op- + tions does have data, it must be given in the first form, using an equals character. Otherwise pcre2grep will assume that it has no data. USING PCRE2'S CALLOUT FACILITY - pcre2grep has, by default, support for calling external programs or - scripts or echoing specific strings during matching by making use of - PCRE2's callout facility. However, this support can be completely or - partially disabled when pcre2grep is built. You can find out whether - your binary has support for callouts by running it with the --help op- - tion. If callout support is completely disabled, all callouts in pat- + pcre2grep has, by default, support for calling external programs or + scripts or echoing specific strings during matching by making use of + PCRE2's callout facility. However, this support can be completely or + partially disabled when pcre2grep is built. You can find out whether + your binary has support for callouts by running it with the --help op- + tion. If callout support is completely disabled, all callouts in pat- terns are ignored by pcre2grep. If the facility is partially disabled, - calling external programs is not supported, and callouts that request + calling external programs is not supported, and callouts that request it are ignored. - A callout in a PCRE2 pattern is of the form (?C) where the argu- - ment is either a number or a quoted string (see the pcre2callout docu- - mentation for details). Numbered callouts are ignored by pcre2grep; + A callout in a PCRE2 pattern is of the form (?C) where the argu- + ment is either a number or a quoted string (see the pcre2callout docu- + mentation for details). Numbered callouts are ignored by pcre2grep; only callouts with string arguments are useful. Echoing a specific string - Starting the callout string with a pipe character invokes an echoing + Starting the callout string with a pipe character invokes an echoing facility that avoids calling an external program or script. This facil- - ity is always available, provided that callouts were not completely - disabled when pcre2grep was built. The rest of the callout string is - processed as a zero-terminated string, which means it should not con- - tain any internal binary zeros. It is written to the output, having - first been passed through the same escape processing as text from the - --output (-O) option (see above). However, $0 cannot be used to insert - a matched substring because the match is still in progress. Instead, - the single character '0' is inserted. Any syntax errors in the string - (for example, a dollar not followed by another character) causes the - callout to be ignored. No terminator is added to the output string, so - if you want a newline, you must include it explicitly using the escape + ity is always available, provided that callouts were not completely + disabled when pcre2grep was built. The rest of the callout string is + processed as a zero-terminated string, which means it should not con- + tain any internal binary zeros. It is written to the output, having + first been passed through the same escape processing as text from the + --output (-O) option (see above). However, $0 cannot be used to insert + a matched substring because the match is still in progress. Instead, + the single character '0' is inserted. Any syntax errors in the string + (for example, a dollar not followed by another character) causes the + callout to be ignored. No terminator is added to the output string, so + if you want a newline, you must include it explicitly using the escape $n. For example: pcre2grep '(.)(..(.))(?C"|[$1] [$2] [$3]$n")' - Matching continues normally after the string is output. If you want to - see only the callout output but not any output from an actual match, + Matching continues normally after the string is output. If you want to + see only the callout output but not any output from an actual match, you should end the pattern with (*FAIL). Calling external programs or scripts This facility can be independently disabled when pcre2grep is built. It - is supported for Windows, where a call to _spawnvp() is used, for VMS, - where lib$spawn() is used, and for any Unix-like environment where + is supported for Windows, where a call to _spawnvp() is used, for VMS, + where lib$spawn() is used, and for any Unix-like environment where fork() and execv() are available. If the callout string does not start with a pipe (vertical bar) charac- - ter, it is parsed into a list of substrings separated by pipe charac- - ters. The first substring must be an executable name, with the follow- + ter, it is parsed into a list of substrings separated by pipe charac- + ters. The first substring must be an executable name, with the follow- ing substrings specifying arguments: executable_name|arg1|arg2|... - Any substring (including the executable name) may contain escape se- - quences started by a dollar character. These are the same as for the + Any substring (including the executable name) may contain escape se- + quences started by a dollar character. These are the same as for the --output (-O) option documented above, except that $0 cannot insert the - matched string because the match is still in progress. Instead, the + matched string because the match is still in progress. Instead, the character '0' is inserted. If you need a literal dollar or pipe charac- ter in any substring, use $$ or $| respectively. Here is an example: @@ -962,43 +968,43 @@ USING PCRE2'S CALLOUT FACILITY Arg1: [1] [234] [4] Arg2: |1| () 12345 - The parameters for the system call that is used to run the program or + The parameters for the system call that is used to run the program or script are zero-terminated strings. This means that binary zero charac- - ters in the callout argument will cause premature termination of their - substrings, and therefore should not be present. Any syntax errors in - the string (for example, a dollar not followed by another character) + ters in the callout argument will cause premature termination of their + substrings, and therefore should not be present. Any syntax errors in + the string (for example, a dollar not followed by another character) causes the callout to be ignored. If running the program fails for any - reason (including the non-existence of the executable), a local match- + reason (including the non-existence of the executable), a local match- ing failure occurs and the matcher backtracks in the normal way. MATCHING ERRORS - It is possible to supply a regular expression that takes a very long - time to fail to match certain lines. Such patterns normally involve - nested indefinite repeats, for example: (a+)*\d when matched against a - line of a's with no final digit. The PCRE2 matching function has a re- - source limit that causes it to abort in these circumstances. If this - happens, pcre2grep outputs an error message and the line that caused - the problem to the standard error stream. If there are more than 20 + It is possible to supply a regular expression that takes a very long + time to fail to match certain lines. Such patterns normally involve + nested indefinite repeats, for example: (a+)*\d when matched against a + line of a's with no final digit. The PCRE2 matching function has a re- + source limit that causes it to abort in these circumstances. If this + happens, pcre2grep outputs an error message and the line that caused + the problem to the standard error stream. If there are more than 20 such errors, pcre2grep gives up. - The --match-limit option of pcre2grep can be used to set the overall - resource limit. There are also other limits that affect the amount of - memory used during matching; see the discussion of --heap-limit and + The --match-limit option of pcre2grep can be used to set the overall + resource limit. There are also other limits that affect the amount of + memory used during matching; see the discussion of --heap-limit and --depth-limit above. DIAGNOSTICS Exit status is 0 if any matches were found, 1 if no matches were found, - and 2 for syntax errors, overlong lines, non-existent or inaccessible - files (even if matches were found in other files) or too many matching + and 2 for syntax errors, overlong lines, non-existent or inaccessible + files (even if matches were found in other files) or too many matching errors. Using the -s option to suppress error messages about inaccessi- ble files does not affect the return code. - When run under VMS, the return code is placed in the symbol - PCRE2GREP_RC because VMS does not distinguish between exit(0) and + When run under VMS, the return code is placed in the symbol + PCRE2GREP_RC because VMS does not distinguish between exit(0) and exit(1). @@ -1010,11 +1016,11 @@ SEE ALSO AUTHOR Philip Hazel - University Computing Service + Retired from University Computing Service Cambridge, England. REVISION - Last updated: 04 October 2020 - Copyright (c) 1997-2020 University of Cambridge. + Last updated: 31 August 2021 + Copyright (c) 1997-2021 University of Cambridge. diff --git a/src/pcre2grep.c b/src/pcre2grep.c index 02d2e39..f233c1d 100644 --- a/src/pcre2grep.c +++ b/src/pcre2grep.c @@ -423,6 +423,7 @@ used to identify them. */ #define N_OM_SEPARATOR (-22) #define N_MAX_BUFSIZE (-23) #define N_OM_CAPTURE (-24) +#define N_ALLABSK (-25) static option_item optionlist[] = { { OP_NODATA, N_NULL, NULL, "", "terminate options" }, @@ -490,6 +491,7 @@ static option_item optionlist[] = { { OP_NODATA, 'v', NULL, "invert-match", "select non-matching lines" }, { OP_NODATA, 'w', NULL, "word-regex(p)", "force patterns to match only as words" }, { OP_NODATA, 'x', NULL, "line-regex(p)", "force patterns to match only whole lines" }, + { OP_NODATA, N_ALLABSK, NULL, "allow-lookaround-bsk", "allow \\K in lookarounds" }, { OP_NODATA, 0, NULL, NULL, NULL } }; @@ -3544,7 +3546,7 @@ return rc; /************************************************* -* Handle a single-letter, no data option * +* Handle a no-data option * *************************************************/ static int @@ -3557,6 +3559,7 @@ switch(letter) case N_LBUFFER: line_buffered = TRUE; break; case N_LOFFSETS: line_offsets = number = TRUE; break; case N_NOJIT: use_jit = FALSE; break; + case N_ALLABSK: extra_options |= PCRE2_EXTRA_ALLOW_LOOKAROUND_BSK; break; case 'a': binary_files = BIN_TEXT; break; case 'c': count_only = TRUE; break; case 'F': options |= PCRE2_LITERAL; break;